The inaugural lecture of Prof. Decebal Mocanu entitled “Sparse Artificial Neural Networks” will take place on 30 September 2024 on Belval Campus.
Presentation
Artificial Intelligence is becoming both a blessing and a burden, thanks to the power of artificial neural networks. The lecture starts with a quick overview of my research line and the challenges encountered by the modern artificial neural network models. Next, it introduces in more details one of these challenges (the dense connectivity) which prevents us from having scalable and efficient artificial neural networks at both cloud and edge computing levels. An emerging state-of-the-art solution is presented, i.e., sparse-to-sparse training, which reduces the number of connections quadratically while persistently improving performance and generalization. The discussion begins with the first works on static and dynamic sparse training in the typical single task (un)supervised learning context. Further, it gradually introduces newer approaches in the more challenging contexts of continual and reinforcement learning. Besides the fundamental theoretical novelty, a glimpse into the future, such as truly sparse implementations and deep learning energy efficiency, is also provided and open for discussion.
Biography
Decebal Mocanu is an Associate Professor in Machine Learning within the Department of Computer Science at the University of Luxembourg, where he leads the Blue Neural Networks group. He is also a Guest Faculty Member within the Mathematics and Computer Science department at the Eindhoven University of Technology (TU/e) and an alumni member of TU/e’s Young Academy of Engineering. Previously, he worked as an Assistant Professor in Machine Learning at TU/e (2017-2020) and at the University of Twente (2020-2023). In 2017, Decebal received his PhD degree from TU/e. During his doctoral studies and afterwards, Decebal undertook four research visits: at the University of Pennsylvania (2014), Julius Maximilians University of Würzburg (2015), the University of Texas at Austin (2016), and the University of Alberta (2022). In the long term, Decebal is interested in studying the synergy between artificial intelligence, neuroscience, and network science for the benefit of science and society.
Programme
- 17:30 Welcome speech – Pascal Bouvry, Dean, Faculty of Science, Technology and Medicine
- 17:35 Lecture “Sparse artificial neural networks” – Decebal Mocanu, Associate Professor in Machine Learning
- 18:15 Q&A
- 18:30 Cocktail